Constant-Time Gaussian Filtering for Acceleration of Structure Similarity

Tomohiro Sasaki, Norishige Fukushima, Yoshihiro Maeda, Kenjiro Sugimoto, Sei Ichiro Kamata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

In this paper, we propose an acceleration method of structural similarity (SSIM) and its multi-scaled version, called MS-SSIM. The calculation process of SSIM and MS-SSIM includes multiple Gaussian filters, and the cost of the filter is dominant for the entire process; thus, to accelerate SSIM/MS-SSIM, we replace Gaussian filtering using convolution with sliding DCT. Gaussian filter based on sliding DCT is faster than the usual convolution method. Besides, its computational complexity does not depend on the filter window length. Also, naive implementations of SSIM and MS-SSIM scan image many times for the pixel-wise operation; however, these operations can be incorporated into Gaussian filtering. Thus, we optimize the processing pipeline to achieve high cache-efficiency. As a result, the proposed SSIM computation was accelerated by 6.36 times and MS-SSIM by 8.11 times faster than the conventional approach.

Original languageEnglish
Title of host publicationProceedings of International Conference on Image Processing and Robotics, ICIPRoB 2020
EditorsB. H. Sudantha
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728165417
DOIs
Publication statusPublished - 2020 Mar 6
Event1st International Conference on Image Processing and Robotics, ICIPRoB 2020 - Negombo, Sri Lanka
Duration: 2020 Mar 62020 Mar 8

Publication series

NameProceedings of International Conference on Image Processing and Robotics, ICIPRoB 2020

Conference

Conference1st International Conference on Image Processing and Robotics, ICIPRoB 2020
Country/TerritorySri Lanka
CityNegombo
Period20/3/620/3/8

Keywords

  • SSIM
  • acceleration
  • constant-time Gaussian filtering
  • fast image quality assessment
  • sliding DCT

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Decision Sciences (miscellaneous)
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Constant-Time Gaussian Filtering for Acceleration of Structure Similarity'. Together they form a unique fingerprint.

Cite this